Ethan He
speaker
722 appearances
1 recordings
1 series
first heard Jun 2026
last heard 1 Jun
Ethan He’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 1 in all, peaking in Jun 2026 with 1.
Appearances
But usually they're not relevant to the video itself.
and say maybe like the video is a natural scene of mountains or something, and the title is like, I'm so happy today.
So they have no correlation at all.
So the first step is to, you have to generate a synthetic pair of language with videos.
So you got the videos from the internet and you,
you use a VLM to caption the videos.
So that part, here's the question, how do you get the VLM to begin with?
Say if there's no VLM exists, how do you generate the text to the beginning?
It's impossible.
I see.
In the beginning, it's like you ask human to describe the video as detailed as possible.
For example, you ask them to describe everything, like all objects, all characters, and all interaction and dialogues in the videos.
So that's in the protocol of Cosmos Labeling.
We require the...
The objective we gave to the labelers was that you have to describe the video as detailed as possible, such that a blind person hears a blob of text, can reconstruct what the video is from their head.
Video or image?
You're talking about images?
Video or image, either one of them.
Yeah, yeah.
It's interesting to see that you kind of need both data.
Showing 81–100 of 722 · page 5 of 37
← Previous
Next →